CtrlK
BlogDocsLog inGet started
Tessl Logo

zero-day-discovery

0day自主发现引擎:变体分析/补丁间隙/差分/Fuzzing/污点推理/N-day武器化/猎人思维。Use when public vulns not found and need to discover 0day or weaponize N-day.

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/zero-day-discovery/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is information-dense and methodologically rich, but it is presented as one unstructured code block with no executable examples, no section navigation, and only an end-of-document validation checklist. Restructuring and adding concrete tool invocations would materially improve it.

Suggestions

Break the single code block into markdown sections (## 变体分析, ## 补丁间隙, ## Fuzzing, etc.) so the methodology is navigable rather than a wall of text.

Add at least one concrete, executable example per high-yield path — e.g. a sample CodeQL query for taint reasoning or an AFL++ harness command — instead of only naming the tools.

Insert explicit validation checkpoints inside each workflow (e.g. confirm the grep hit is in an unreached code path before claiming 0day) rather than only a single global verification checklist at the end.

DimensionReasoningScore

Conciseness

The body is token-dense and assumes Claude's competence — it never explains what Fuzzing, taint analysis, or diffing is — so every line adds non-obvious methodological value, matching the lean-and-efficient anchor.

3 / 3

Actionability

It names concrete tools (AFL++/libFuzzer, boofuzz, radamsa, restler, CodeQL, Semgrep, Joern, bindiff, diaphora) and gives a procedure ("拿一个CVE补丁→提炼漏洞模式→全库grep"), but provides no executable code, commands, or copy-paste examples, fitting the some-guidance-but-incomplete anchor.

2 / 3

Workflow Clarity

Each of the five paths has an internal sequence and a closing "0day验证" checklist (可复现/根因清楚/影响可证/排除误报), but there are no explicit error-recovery checkpoints or validate→fix→retry feedback loops within the workflows, matching the steps-present-but-checkpoints-implicit anchor.

2 / 3

Progressive Disclosure

The entire body is a single monolithic code block with no markdown section headers, navigation, or file references — a wall of text matching the monolithic-wall anchor rather than the well-organized-sections exception for short skills.

1 / 3

Total

8

/

12

Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-triggered description that clearly conveys a niche capability and when to invoke it. Its main weakness is trigger-term breadth, relying on jargon over the everyday phrasings a user might naturally say.

Suggestions

Add common user-facing trigger terms such as "exploit", "CVE", "find vulnerability", or "PoC" alongside the technical jargon to broaden natural-language matching.

Keep the bilingual phrasing but ensure the English portion carries the primary trigger clause for consistent matching across users.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — "变体分析/补丁间隙/差分/Fuzzing/污点推理/N-day武器化/猎人思维" — each a distinct actionable technique, matching the score-3 anchor of multiple specific concrete actions.

3 / 3

Completeness

Explicitly states both what it does (the enumerated techniques) and when to use it via the "Use when public vulns not found and need to discover 0day or weaponize N-day" clause, satisfying the both-what-and-when anchor.

3 / 3

Trigger Term Quality

Relevant niche terms like "0day", "N-day", "weaponize", "public vulns" appear, but common variations a user might actually say ("exploit", "CVE", "find vulnerability", "PoC") are missing, so coverage is partial.

2 / 3

Distinctiveness Conflict Risk

The 0day/N-day discovery niche is highly specific with distinct triggers unlikely to overlap with general security or code-review skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
Ed1s0nZ/CyberStrikeAI
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.